Burnsnet: Burn region segmentation network from color images with two-way CNN

Chauhan, Joohi, Rosin, Paul L. ORCID: https://orcid.org/0000-0002-4965-3884 and Goyal, Puneet 2024. Burnsnet: Burn region segmentation network from color images with two-way CNN. Presented at: 2024 International Conference on Image Processing (ICIP), Abu Dhabi, United Arab Emirates, 27-30 October 2024. Proceedings of 2024 International Conference on Image Processing. , vol.41 pp. 3172-3178. 10.1109/icip51287.2024.10647789

PDF - Accepted Post-Print Version Download (799kB)

Abstract

Burn injury is a serious health issue leading to several thousands of annual fatalities. The color image-based automated burns diagnostic and assessment methods hold the potential for timely diagnosis and treatment. However, the research is limited in this domain which remains a major challenge. In this work, we explore and address the complex task of burn region segmentation in color images of burn patients. We present a semantic segmentation network that has two parallel sub-networks: a spatial-stream network for extracting low-level features and a contextual-stream network for generating a larger receptive field. Our network utilizes the pre-trained ResNet101 network, global average pooling, and instance normalization for better encoding and fusion of the network outputs. This dual-stream approach optimizes the performance in situations where data scarcity poses a challenge, facilitating robust semantic segmentation despite limited training samples. We prepared a pixel-wise labeled dataset for burn region segmentation and the experimental results on this dataset show that our proposed network outperforms several state-of-the-art semantic segmentation methods. Our method achieved mIOU and Matthews’ correlation coefficient (MCC) of 74.3% and 81.7%, respectively, approximately 4.5% higher than the second-best performing method. The Extended Burn Image Segmentation (EBIS) dataset and our model are available at https://github.com/VEDAs-Lab/EBIS

Item Type:	Conference or Workshop Item (Paper)
Date Type:	Published Online
Status:	Published
Schools:	Computer Science & Informatics
ISBN:	9798350349405
ISSN:	2381-8549
Date of First Compliant Deposit:	10 October 2024
Date of Acceptance:	6 June 2024
Last Modified:	09 Nov 2024 02:45
URI:	https://orca.cardiff.ac.uk/id/eprint/172783

Actions (repository staff only)

Edit Item